Machine learning and RSM models for prediction of compressive strength of smart bio-concrete

被引:25
作者
Algaifi, Hassan Amer [1 ]
Abu Bakar, Suhaimi [2 ]
Alyousef, Rayed [3 ]
Sam, Abdul Rahman Mohd [2 ]
Alqarni, Ali S. [5 ]
Ibrahim, M. H. Wan [1 ]
Shahidan, Shahiron [1 ]
Ibrahim, Mohammed [4 ]
Salami, Babatunde Abiodun [4 ]
机构
[1] Univ Tun Hussein Onn Malaysia, Fac Civil & Environm Engn, Parit Raja 86400, Johor, Malaysia
[2] Univ Teknol Malaysia, Fac Engn, Sch Civil Engn, Johor Baharu 81310, Malaysia
[3] Prince Sattam Bin Abdulaziz Univ, Coll Engn, Dept Civil Engn, Alkharj 11942, Saudi Arabia
[4] King Fand Univ Petr & Minerals, Ctr Engn Res, Res Inst, Dhahran 31261, Saudi Arabia
[5] King Saud Univ, Coll Engn, Dept Civil Engn, Riyadh 11421, Saudi Arabia
关键词
concrete strength; machine learning; response surface methodology; self-healing concrete; RESPONSE-SURFACE METHODOLOGY; FLY-ASH; NEURAL-NETWORK; GEOPOLYMER CONCRETE; PRECIPITATION; BACTERIA; ANN; MICROSTRUCTURE; OPTIMIZATION; PERMEABILITY;
D O I
10.12989/sss.2021.28.4.535
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
In recent years, bacteria-based self-healing concrete has been widely exploited to improve the compressive strength of concrete using different bacterial species. However, both the identification of the optimal involved reaction parameters and theoretical framework information are still limited. In the present study, both experimentally and numerical modelling using machine learning (ANN and ANFIS) and response surface methodology (RSM) were implemented to evaluate and optimse the evolution of bacterial concrete strength. Therefore, a total of 58 compressive strength tests of the concrete incorporating new bacterial species were designed using different concentrations of urea, cells concentration, calcium, nutrient and time. Based on the results, the compressive strength of the bacterial concrete improved by 16% due to the decrement of the pore percentage in the concrete skin; specifically, 5 mm from the concrete surface, compared to that of the control concrete. In the same context, both machine the learning and RSM models indicated that the optimal range of urea, calcium, nutrient and bacterial cells were (18-23 g/L), (150-350 mM), (1-3 g/L) and 2x 10(7) cells/mL, respectively. Based on the statistical analysis, RMSE, R-2, MPE, RAE and RRSE were (0.793, 0.785), (0.985, 0.986), (1.508, 1.1), (0.11, 0.09) and (0.121, 0.12) from both the ANN and ANFIS models, respectively, while; the following values (0.839, 0.972, 1.678, 0.131 and 0.165) was obtained from RSM model, respectively. As such, it can be concluded that a high correlation and minimum error were obtained, however, machine learning models provided more accurate results compared to that of the RSM model.
引用
收藏
页码:535 / 551
页数:17
相关论文
共 71 条
[1]   P-value significance level test for high-performance steel fiber concrete (HPSFC) [J].
Abubakar, Abdulhameed U. ;
Akcaoglu, Tulin ;
Marar, Khaled .
COMPUTERS AND CONCRETE, 2018, 21 (05) :485-493
[2]   Modeling of Compressive Strength of Sustainable Self-Compacting Concrete Incorporating Treated Palm Oil Fuel Ash Using Artificial Neural Network [J].
Al-Mughanam, Tawfiq ;
Aldhyani, Theyazn H. H. ;
Alsubari, Belal ;
Al-Yaari, Mohammed .
SUSTAINABILITY, 2020, 12 (22) :1-13
[3]   Engineering Properties of Waste Sawdust-Based Lightweight Alkali-Activated Concrete: Experimental Assessment and Numerical Prediction [J].
Alabduljabbar, Hisham ;
Huseien, Ghasan Fahim ;
Sam, Abdul Rahman Mohd ;
Alyouef, Rayed ;
Algaifi, Hassan Amer ;
Alaskar, Abdulaziz .
MATERIALS, 2020, 13 (23) :1-30
[4]   Bio-inspired self-healing of concrete cracks using new B. pseudomycoides species [J].
Algaifi, Hassan Amer ;
Bakar, Suhaimi Abu ;
Alyousef, Rayed ;
Sam, Abdul Rahman Mohd ;
Ibrahim, M. H. Wan ;
Shahidan, Shahiron ;
Ibrahim, Mohammed ;
Salami, Babatunde Abiodun .
JOURNAL OF MATERIALS RESEARCH AND TECHNOLOGY-JMR&T, 2021, 12 :967-981
[5]   Insight into the role of microbial calcium carbonate and the factors involved in self-healing concrete [J].
Algaifi, Hassan Amer ;
Abu Bakar, Suhaimi ;
Sam, Abdul Rahman Mohd ;
Ismail, Mohammad ;
Abidin, Ahmad Razin Zainal ;
Shahir, Shafinaz ;
Altowayti, Wahid Ali Hamood .
CONSTRUCTION AND BUILDING MATERIALS, 2020, 254
[6]   Numerical modeling for crack self-healing concrete by microbial calcium carbonate [J].
Algaifi, Hassan Amer ;
Abu Bakar, Suhaimi ;
Sam, Abdul Rahman Mohd ;
Abidin, Ahmad Razin Zainal ;
Shahir, Shafinaz ;
AL-Towayti, Wahid Ali Hamood .
CONSTRUCTION AND BUILDING MATERIALS, 2018, 189 :816-824
[7]   Prediction of the compressive strength of fly ash geopolymer concrete using gene expression programming [J].
Alkroosh, Iyad S. ;
Sarker, Prabir K. .
COMPUTERS AND CONCRETE, 2019, 24 (04) :295-302
[8]   Optimisation of carbon dioxide sequestration into bio-foamed concrete bricks pores using Bacillus tequilensis [J].
Alshalif, Abdullah Faisal ;
Irwan, J. M. ;
Othman, N. ;
Al-Gheethi, A. A. ;
Shamsudin, S. ;
Nasser, Ibrahim M. .
JOURNAL OF CO2 UTILIZATION, 2021, 44
[9]   The adsorptive removal of As (III) using biomass of arsenic resistant Bacillus thuringiensis strain WS3: Characteristics and modelling studies [J].
Altowayti, Wahid Ali Hamood ;
Algaifi, Hassan Amer ;
Abu Bakar, Suhaimi ;
Shahir, Shafinaz .
ECOTOXICOLOGY AND ENVIRONMENTAL SAFETY, 2019, 172 :176-185
[10]   Comparison of response surface methodology and hybrid-training approach of artificial neural network in modelling the properties of concrete containing steel fibre extracted from waste tyres [J].
Awolusi, Temitope F. ;
Oke, Oluwaseyi L. ;
Akinkurolere, Olufunke O. ;
Atoyebi, Olumoyewa D. .
COGENT ENGINEERING, 2019, 6 (01)